{"id":"W2917760294","doi":"10.1007/s11116-019-09985-7","title":"Assessment of the transit ridership prediction errors using AVL/APC data","year":2019,"lang":"en","type":"article","venue":"Transportation","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Korea Transport Institute; Yonsei University","keywords":"Computer science; Mode choice; Mode (computer interface); Transit (satellite); Data collection; Scale (ratio); Data mining; Market segmentation; Data quality; Regression analysis; Component (thermodynamics); Econometrics; Service (business); Transport engineering; Statistics; Engineering; Machine learning; Public transport; Geography; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006653575,0.00008058224,0.0001335703,0.00003207825,0.0001798097,0.00001635378,0.0004170822,0.00008317388,0.0004180113],"category_scores_gemma":[0.000007030008,0.00006498596,0.00007368722,0.0003093398,0.0001344714,0.0006311064,0.000002177302,0.0001227742,0.000001990696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004566105,"about_ca_system_score_gemma":0.0002538824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003203316,"about_ca_topic_score_gemma":0.01208207,"domain_scores_codex":[0.9986923,0.00008748809,0.000314614,0.0002563304,0.0004899235,0.0001592831],"domain_scores_gemma":[0.9992821,0.0000342819,0.000146991,0.0004269653,0.00006845134,0.00004123385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001052493,0.00004868078,0.9921598,0.00005213055,0.00001441753,1.982622e-7,0.003735318,0.0007751499,0.001709547,0.001245424,0.00001432694,0.0002344285],"study_design_scores_gemma":[0.0002590713,0.00001357832,0.9953343,0.00003925941,0.00009021371,1.877646e-8,0.001469099,0.001560897,0.0002458361,0.0003436369,0.0005741882,0.00006986142],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930473,0.00002662823,0.002741632,0.0002622364,0.0004609546,0.0004622019,0.0002070593,0.0000405207,0.002751447],"genre_scores_gemma":[0.9991225,0.000008995904,0.0003730209,0.00002336982,0.00005878983,0.000002305787,0.0002189802,0.000008014867,0.0001840118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008878757,"threshold_uncertainty_score":0.674208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08815460423002847,"score_gpt":0.3631642501689654,"score_spread":0.275009645938937,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}